I write about reinforcement learning, ML, and rebuilding things from scratch to actually understand them.
Intro to Value and Policy Iteration
This is a sample post. Delete it once you’ve written your first real one. Notes math: true in the front matter turns on KaTeX for this page. Code blocks get a copy button automatically. Set draft: false to publish.
Q-Learning From Scratch
Building tabular Q-learning from the ground up to actually understand the update rule.